Intelligent early warning system for dynamic exacerbation of chronic obstructive pulmonary disease

Abstract

The present application relates to the technical field of health care, in particular to an intelligent early warning system for dynamic exacerbation of chronic obstructive pulmonary disease, which is used to solve the technical problem of inaccurate assessment of lung ventilation capacity of users in the prior art. The system comprises: a data acquisition unit for acquiring lung function time series data and multi-dimensional physiological time series data of a target user in an observation period; the observation period comprises a plurality of consecutive days; a processing unit for determining suspected abnormal days according to the lung function time series data, determining the deviation degree of the multi-dimensional physiological time series data of the suspected abnormal days and the multi-dimensional physiological time series data of the reference days and the similarity of the different dimensional physiological time series data deviation degrees, determining the abnormal days from the suspected abnormal days based on the deviation degree and the similarity, and determining the dynamic exacerbation risk level of the target user's chronic obstructive pulmonary disease based on the abnormal days; and performing risk warning based on the dynamic exacerbation risk level of the target user's chronic obstructive pulmonary disease.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical care, in particular to an intelligent early warning system for dynamic exacerbation of chronic obstructive pulmonary disease. BACKGROUND

[0002] The existing detection method for dynamic exacerbation of chronic obstructive pulmonary disease is: according to the forced expiratory volume in one second (FEV1) and forced vital capacity (FVC) ratio (FEV1 / FVC ratio) in the lung function data of a user, the ventilation capacity of the user's lung is evaluated, and then the doctor takes the ventilation capacity of the user's lung as the basis, and combines the current physical state of the user and the relevant experience of the doctor to warn the dynamic exacerbation of the user's chronic obstructive pulmonary disease. However, the ventilation capacity of the user's body is often affected by various factors such as cold, physical exhaustion, etc., and the single FEV1 / FVC ratio cannot accurately reflect the ventilation capacity of the user's lung, resulting in inaccurate evaluation of the ventilation capacity of the user's lung. SUMMARY

[0003] In order to solve the technical problem of inaccurate evaluation of the ventilation capacity of the user's lung in the prior art, the purpose of the present application is to provide an intelligent early warning system for dynamic exacerbation of chronic obstructive pulmonary disease, which comprises a data acquisition unit and a processing unit.

[0004] The data acquisition unit is used to acquire the lung function time series data and multi-dimensional physiological time series data of the target user in the observation stage; the observation stage includes a plurality of consecutive dates.

[0005] The processing unit is used to determine a suspected abnormal day according to the lung function time series data, the suspected abnormal day being a date with a lung function data change degree greater than a first threshold; determine the deviation degree of the multi-dimensional physiological time series data of the suspected abnormal day and the multi-dimensional physiological time series data of a reference day and the similarity of the deviation degrees of different dimensional physiological time series data, the reference day being a date with the smallest lung function data abnormal value and the best lung ventilation function; determine an abnormal day from the suspected abnormal day based on the deviation degree and the similarity, and determine the risk level of the dynamic exacerbation of chronic obstructive pulmonary disease of the target user based on the abnormal day; and perform risk warning based on the risk level of the dynamic exacerbation of chronic obstructive pulmonary disease of the target user.

[0006] As a possible implementation manner, the lung function time series data includes the forced expiratory volume in one second and the forced vital capacity of each day within a plurality of days; the processing unit is specifically used to: calculate the first ratio of the forced expiratory volume in one second and the forced vital capacity of each day; take the normalized value of the difference between the first ratio of each day and the first ratio of the previous day as the initial abnormal value of the lung function data of each day; and mark the date with the initial abnormal value greater than the first threshold as a suspected abnormal day.

[0007] As a possible implementation manner, the processing unit is further configured to: mark a date with an initial abnormal value less than or equal to the first threshold value as an initial normal day; take a plurality of continuous adjacent initial normal days as a plurality of stable disease stages; select a stable disease stage with the most initial normal days from the plurality of stable disease stages as a reference stage; calculate a ventilation function of the target user on each day in the reference stage, the ventilation function being positively correlated with the first ratio and negatively correlated with the initial abnormal value; and take an initial normal day with the largest ventilation function value in the reference stage as a reference day.

[0008] As a possible implementation manner, the processing unit is specifically configured to: fit the target-dimension physiological time-series data of the target suspected abnormal day to obtain a first fitting curve, and fit the target-dimension physiological time-series data of the reference day to obtain a second fitting curve; the target suspected abnormal day is one of the plurality of suspected abnormal days, and the target-dimension physiological time-series data is physiological time-series data of one dimension of the multi-dimension physiological time-series data; calculate an absolute value of a data difference between the first fitting curve and the second fitting curve at each time point, and a trend weight at each time point, wherein the trend weight is a first value if the slope directions of the first fitting curve and the second fitting curve at a time point are the same, and the trend weight is a second value if the slope directions of the first fitting curve and the second fitting curve at the time point are different, and the second value is greater than the first value; based on the trend weight at each time point, sum the absolute values of the data differences at the time point after weighting, and normalize the sum to obtain a deviation degree of the target suspected abnormal day in the target dimension.

[0009] As a possible implementation manner, the processing unit is specifically configured to: determine a deviation degree time-series sequence of the first-dimension physiological time-series data and a deviation degree time-series sequence of the second-dimension physiological time-series data; the first-dimension physiological time-series data and the second-dimension physiological time-series data are physiological time-series data of different dimensions of the multi-dimension physiological time-series data; and the deviation degree time-series sequence includes deviation degrees at different time points. The processing unit is further configured to: take a similarity between the deviation degree time-series sequence of the first-dimension physiological time-series data and the deviation degree time-series sequence of the second-dimension physiological time-series data as a similarity between the first-dimension physiological time-series data and the second-dimension physiological time-series data.

[0010] As a possible implementation manner, the processing unit is specifically configured to: based on the deviation degree of the target suspected abnormal day, an average of the similarities of the target suspected abnormal day in all dimensions of physiological time-series data, and a number of interval days between the target suspected abnormal day and the reference day, calculate an updated abnormal value of the target suspected abnormal day, the updated abnormal value being positively correlated with the deviation degree and the average of the similarities, and negatively correlated with the number of interval days; and if the updated abnormal value of the target suspected abnormal day is greater than a second threshold value, mark the target suspected abnormal day as an abnormal day.

[0011] As a possible implementation manner, the processing unit is specifically configured to: determine at least one illness exacerbation phase of the target user based on the abnormal days in the observation phase, the illness exacerbation phase including a plurality of continuous abnormal days; and determine a risk level of the target user based on an exacerbation intensity of the illness exacerbation phase, an illness management capability, and a time interval of adjacent illness exacerbation phases, wherein the exacerbation intensity is used to represent a severity and duration of the illness exacerbation phase, and the illness management capability is used to represent an ability of the target user to control and maintain the illness.

[0012] As a possible implementation manner, the processing unit is specifically configured to: determine an updated abnormal value of each abnormal day in any illness exacerbation phase; fit a third fitting curve based on the updated abnormal values of the illness exacerbation phase, and determine a slope normalization value of each abnormal day in the illness exacerbation phase based on the third fitting curve; multiply the updated abnormal value of any abnormal day by the slope normalization value to obtain a first product; accumulate the first products of each abnormal day to obtain a first accumulated value; calculate a time proportion of the illness exacerbation phase in the observation phase; and take a product of the first accumulated value and the time proportion as the exacerbation intensity of any illness exacerbation phase.

[0013] As a possible implementation manner, the processing unit is specifically configured to: determine an exacerbation intensity of any illness exacerbation phase, a slope normalization value of an exacerbation trend, and a duration of an illness stable phase after any illness exacerbation phase, wherein the slope normalization value of the exacerbation trend is a normalization value of a slope of a fitting straight line obtained by linear fitting of updated abnormal values of the illness exacerbation phase; the illness stable phase includes a plurality of continuous normal days; and the normal day is a date in the observation phase other than the abnormal day; multiply the exacerbation intensity of any illness exacerbation phase by the corresponding slope normalization value to obtain a second product; multiply the second product by a reciprocal of the duration of the illness stable phase to obtain a third product; take an inverse of the third product as an index, calculate a power of a natural constant e, and obtain the illness management capability.

[0014] As a possible implementation manner, the processing unit is specifically configured to: fit a time sequence of the time intervals of adjacent illness exacerbation phases, and take a normalization value of a slope of a fitting straight line as an exacerbation interval trend; take a product of a reciprocal of the illness management capability and a reciprocal of the exacerbation interval trend as a basic risk value; take a reciprocal of a time interval between a most recent illness exacerbation phase closest to a current time and the current time as a time-sensitive factor; multiply the basic risk value by the time-sensitive factor, and normalize the product to determine the risk level of the target user.

[0015] The application has the following beneficial effects: the application verifies the abnormal situation of the lung function data of a user by taking the deviation of multi-dimensional physiological time sequence data from a reference day and the similarity of the deviations between different dimensions as a verification mechanism, determines an abnormal day where an abnormality exists, and further determines a risk level of dynamic exacerbation of the chronic obstructive pulmonary disease of the user according to the abnormal day. Based on this, the application can effectively identify false abnormalities of lung function data caused by factors such as colds and physical exhaustion, thereby significantly improving the specificity and accuracy of early warning. BRIEF DESCRIPTION OF DRAWINGS

[0016] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0017] Figure 1 The system architecture diagram of the intelligent early warning system for dynamic exacerbation of chronic obstructive pulmonary disease provided by an embodiment of the present application;

[0018] Figure 2 The flowchart of the intelligent early warning method for dynamic exacerbation of chronic obstructive pulmonary disease provided by an embodiment of the present application. DETAILED DESCRIPTION

[0019] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined object, the following will combine the drawings and the preferred embodiments to specifically describe the intelligent early warning system for dynamic exacerbation of chronic obstructive pulmonary disease according to the present application, its specific implementation, structure, features and effects in detail. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0021] The following will specifically describe the specific scheme of the intelligent early warning system for dynamic exacerbation of chronic obstructive pulmonary disease provided by the present application in combination with the drawings.

[0022] Please refer to Figure 1 which shows the system architecture diagram of the intelligent early warning system for dynamic exacerbation of chronic obstructive pulmonary disease provided by an embodiment of the present application. As shown in Figure 1 , the intelligent early warning system for dynamic exacerbation of chronic obstructive pulmonary disease includes a data acquisition unit 101 and a processing unit 102.

[0023] a data collection unit, configured to collect lung function time series data and multi-dimensional physiological time series data of a target user in an observation period, the observation period including a plurality of consecutive dates;

[0024] a processing unit, configured to determine a suspected abnormal day according to the lung function time series data, the suspected abnormal day being a date with a lung function data change degree greater than a first threshold value; determine a deviation degree of the multi-dimensional physiological time series data of the suspected abnormal day from multi-dimensional physiological time series data of a reference day and a similarity of different dimensional physiological time series data deviation degrees, the reference day being a date with the smallest lung function data abnormal value and the best lung ventilation function; determine an abnormal day from the suspected abnormal days based on the deviation degree and the similarity, and determine a chronic obstructive pulmonary disease condition dynamic exacerbation risk level of the target user based on the abnormal day; and perform a risk warning based on the chronic obstructive pulmonary disease condition dynamic exacerbation risk level of the target user.

[0025] In a possible implementation, since the lung function data of a chronic obstructive pulmonary disease user is easily disturbed by short-term physiological factors, in order to improve the accuracy of the condition dynamic exacerbation warning for the chronic obstructive pulmonary disease user, the application can obtain a long-term lung function data sequence of the user, and reduce the disturbance of non-condition factors in a short period.

[0026] Optionally, the application uses a lung function tester to collect lung function time series data of a target user in an observation period. For example, the application can use a lung function tester to collect the FEV1 / FVC ratio of a user once a day from the time when the user is diagnosed with chronic obstructive pulmonary disease (COPD), to obtain a current FEV1 / FVC ratio sequence of the user. Wherein, FEV1 is the forced expiratory volume in one second, and FVC is the forced vital capacity. The FEV1 / FVC ratio is a recognized core index for COPD diagnosis and severity grading, and is a sensitive index for evaluating whether there is airflow obstruction. The normal value of the FEV1 / FVC ratio is usually above 80%. The greater the FEV1 / FVC ratio, the lighter the degree of expiratory airflow limitation, indicating better airway patency. When the FEV1 / FVC ratio is reduced to <70%, it indicates that there may be persistent airflow limitation. In the application, a smart wearable device such as a smart watch, a smart bracelet, or the like can be used to collect multi-dimensional physiological time series data of the user. For example, the multi-dimensional physiological time series data includes different dimensional data such as blood oxygen saturation, heart rate, and respiratory rate.

[0027] As an implementation, the application can use a decimal scaling standardization method to process the collected lung function time series data and multi-dimensional physiological time series data, so that the processed data has similar scales and distributions, and can be more convenient for subsequent data processing.

[0028] It's important to note that COPD is a chronic disease. As treatment progresses, a user's lung function doesn't gradually improve; instead, it may remain stable or slowly decline. One of the core risks of COPD is acute exacerbations. Acute exacerbations not only lead to a rapid decline in lung function but also significantly increase hospitalization and mortality rates. To avoid this, timely intervention is crucial when early signs of deterioration appear to prevent further progression to acute exacerbations. Early deterioration of lung function in COPD patients involves small, daily abnormal fluctuations on a stable or slowly declining foundation. For example, worsening airway inflammation or sputum blockage might cause the FEV1 / FVC ratio to drop from 62% one day to 59% the next, a daily decrease of 3%. Early identification of such changes allows for timely detection of deterioration signals, preventing further worsening of the condition.

[0029] In this embodiment, the processing unit can perform preliminary screening of the collected lung function time-series data to identify suspected abnormal days. Then, it compares the multi-dimensional physiological time-series data of the suspected abnormal days and normal days to further filter out the actual abnormal days. Furthermore, based on the distribution, trends, and lung function data of the actual abnormal days, this application can further determine the user's COPD risk level, assess whether the user is experiencing early deterioration symptoms, and provide intelligent early warning of dynamic deterioration of COPD based on the risk level.

[0030] The following is a detailed explanation of the process by which the processing unit identifies suspected abnormal days:

[0031] As one possible implementation, the time-series lung function data includes forced expiratory volume in one second (FEV1) and forced vital capacity (FVC) for each day over multiple days; the processing unit is specifically used to: calculate the first ratio of FEV1 to FVC for each day; use the normalized value of the difference between the first ratio of the previous day and the first ratio of the current day as the initial outlier of the daily lung function data; and record the days with initial outliers greater than a first threshold as suspected outlier days.

[0032] As an example, the first threshold is set to 0.5. Specifically, taking the FEV1 / FVC ratio collected on day d as an example, the normalized value of the difference between the FEV1 / FVC ratio on day d-1 and the FEV1 / FVC ratio on day d is calculated and recorded as the outlier of the user's lung function data on day d. .when When the value is greater than or equal to 0.5, day d is recorded as a suspected abnormal day; otherwise, it is recorded as an initial normal day. The specific value of the first threshold can be set by those skilled in the art based on clinical practice or experience, and this application will not elaborate on this.

[0033] Based on this, the application quantifies the initial abnormal value by calculating the normalized difference between the FEV1 / FVC ratio of each day and the ratio of the previous day, and screens the suspected abnormal day accordingly, thereby providing an objective and quantitative preliminary abnormality identification method. This method can sensitively capture the slight but continuous deterioration trend of lung function in the short term, and provides reliable preliminary screening results for subsequent in-depth analysis.

[0034] Next, the process of determining the reference day by the processing unit is described in detail:

[0035] As a possible implementation manner, the processing unit is further configured to: mark the date with the initial abnormal value less than or equal to the first threshold value as an initial normal day; select the disease stable stage with the most initial normal days from the multiple disease stable stages as the reference stage, by taking the consecutive adjacent initial normal days as the disease stable stages; calculate the ventilation function of the target user each day in the reference stage, wherein the ventilation function is positively correlated with the first ratio and negatively correlated with the initial abnormal value; and mark the initial normal day with the maximum ventilation function value in the reference stage as the reference day.

[0036] Optionally, the process can be implemented as follows: in all initial normal days, the consecutive adjacent initial normal days are taken as a disease stable stage. The disease stable stage with the most days is marked as the reference stage. In the reference stage, the product of the target value and the corresponding FEV1 / FVC ratio is calculated , wherein the target value is the reciprocal of the abnormal value of the lung function data of the normal day user when the reciprocal value is not 0; and the target value is the sum of the reciprocal of the abnormal value of the lung function data of the normal day user and a very small value (such as 0.01) when the reciprocal value is 0. The normal day corresponding to the maximum value in all normal days is marked as the reference day. It should be noted that in the reference stage, the multi-dimensional data such as the user's breathing frequency and heart rate are in a stable state, and therefore the reference stage can better reflect the user's true physiological baseline.

[0037] As an index reflecting the health degree of the user's lung function, when the lung function data abnormal value is smaller and the ventilation function is better, it indicates that the user's condition is more stable. The reference day selected in this way is more reliable. When the multi-dimensional data of the suspected abnormal day deviates from the multi-dimensional data in the reference day to a greater extent, it indicates that the condition is less stable, and the probability that such suspected abnormal day is a real abnormal day is greater.

[0038] ​​Based on this, the present application selects the most representative reference day by comprehensively considering the stability of lung function data and the best state of ventilation function in a longest stable stage (reference stage), thereby establishing a highly reliable individualized physiological baseline that truly reflects the best or typical physiological level of the user in a stable state, providing a reliable comparison benchmark for subsequent accurate assessment of the deviation degree of suspected abnormal days, thereby greatly improving the individualized accuracy of abnormality judgment.

[0039] In the following, the process of determining the deviation degree of suspected abnormal days and the similarity of deviation degrees of different dimensional physiological time series data by the processing unit is described in detail:

[0040] As a possible implementation manner, the processing unit is specifically configured to: fit target dimensional physiological time series data of a target suspected abnormal day to obtain a first fitting curve, and fit physiological time series data of the target dimension of the reference day to obtain a second fitting curve; the target suspected abnormal day is one of the multiple suspected abnormal days, and the target dimensional physiological time series data is physiological time series data of one dimension of the multiple dimensional physiological time series data; calculate the absolute value of the data difference of the first fitting curve and the second fitting curve at each time point, and the trend weight at each time point, wherein if the slope direction of the first fitting curve and the second fitting curve is the same at a time point, the value of the trend weight is a first value, otherwise the value of the trend weight is a second value, and the second value is greater than the first value; based on the trend weight at each time point, the absolute value of the difference at the time point is weighted and summed, and the result of the weighted sum is normalized to obtain the deviation degree of the target dimension of the target suspected abnormal day; and the average value of the deviation degrees of the target suspected abnormal day in each dimension is taken as the deviation degree of the target suspected abnormal day.

[0041] As a possible implementation manner, the processing unit is specifically configured to: determine a deviation degree time sequence of the first dimensional physiological time series data and a deviation degree time sequence of the second dimensional physiological time series data; the first dimensional physiological time series data and the second dimensional physiological time series data are respectively physiological time series data of one dimension of the multiple dimensional physiological time series data, and the first dimensional physiological time series data and the second dimensional physiological time series data are different; the deviation degree time sequence includes deviation degrees at multiple different times; and the similarity of the deviation degree time sequence of the first dimensional physiological time series data and the deviation degree time sequence of the second dimensional physiological time series data is taken as the similarity of the first dimensional physiological time series data and the second dimensional physiological time series data.

[0042] For example, the value of the first value is 0.1, and the value of the second value is 1. Optionally, the above process of determining the deviation degree of the suspected abnormal day and determining the similarity can be implemented as follows: taking the wthdimensional data as an example for analysis, the wthdimensional data time sequence of the yth suspected abnormal day is obtained} and the time series sequence of the w-th dimension of the reference day { The least squares method is used to obtain the fitted curves of the two sequences.

[0043] by{ }as well as{ The absolute value of the data difference at time i in} For example, when the slopes of the tangent lines for the w-th dimension at the i-th time point over two days are both positive or both negative, then... Weighting coefficients Record it as 0.1, and conversely, record it as 1.

[0044] Calculate the degree of deviation of the data in the w-th dimension between the y-th suspected abnormal day and the reference day at time i. ,in, Indicates the i-th time point The weight value, This indicates the degree of deviation in the trend of the w-th dimension data at the same time over two days. The larger the value, the more completely opposite the direction of change in the same dimension of data within two days, and the greater the degree of deviation.

[0045] The sequence of deviations of the w-th dimension data between the y-th suspected abnormal day and the reference day at all times is calculated. The average value of all data in this sequence is denoted as the overall deviation of the data in the w-th dimension between the y-th suspected abnormal day and the reference day. Similarly, the deviation sequence of other dimensions of data can be obtained.

[0046] Obtain the similarity of the deviation sequences of any two dimensions of data in the y-th suspected abnormal day. The similarity is denoted as the degree of deviation between the two dimensions of data. As an example, this application can obtain the Pearson correlation coefficient of the deviation sequences of any two dimensions of data, then normalize the Pearson correlation coefficient, and use the normalized result as its similarity. Since the Pearson correlation coefficient ranges from -1 to 1, the normalization method for the Pearson correlation coefficient can be: (Pearson correlation coefficient + 1) / 2.

[0047] It's important to note that the core pathological characteristic of COPD is "airflow limitation and decreased lung ventilation." When COPD users exhibit genuinely abnormal lung function data, the body activates compensatory mechanisms due to worsening airflow limitation. These mechanisms include increasing respiratory rate to compensate for insufficient ventilation and decreasing blood oxygen saturation to reduce oxygen exchange efficiency. Therefore, truly abnormal lung function data in COPD users is often accompanied by synergistic changes across various data dimensions. The more similar the deviations between any two data dimensions, the more synchronized their deviation trends and the stronger the synergy between the dimensions. For example, if an increase in respiratory rate is accompanied by a simultaneous decrease in blood oxygen saturation, it's easier to rule out non-disease-related factors. This suspected abnormal day is more likely an early sign of COPD deterioration and requires close monitoring.

[0048] Based on the above technical solution, this application, when selecting abnormal days from suspected abnormal days, not only considers the specific numerical differences between suspected abnormal days and reference days, but also introduces trend weights to quantify the consistency of the two in the data change trend (slope direction). Higher weights are assigned when trends are opposite, which can effectively capture the compensatory physiological responses of the body in a true pathological state (such as increased breathing to compensate for insufficient ventilation). Combined with the assessment of the similarity of data deviation sequences in different dimensions, the system can identify typical deterioration patterns of multi-system coordinated abnormalities, greatly enhancing its ability to distinguish between true and false abnormalities.

[0049] The following is a detailed explanation of the process by which the processing unit identifies abnormal days from suspected abnormal days:

[0050] As one possible implementation, the processing unit is specifically used to: calculate the updated outlier value of the target suspected outlier day based on the deviation of the target suspected outlier day, the mean similarity of all dimensions of physiological time series data of the target suspected outlier day, and the number of days between the target suspected outlier day and the reference day. The updated outlier value is positively correlated with the deviation and the mean similarity, and negatively correlated with the number of days between the two days. If the updated outlier value of the target suspected outlier day is greater than the second threshold, then the target suspected outlier day is regarded as an outlier day.

[0051] As an example, the second threshold is set to 0.7. Optionally, the process can be specifically implemented as follows: calculating the updated outlier value of the lung function data on the y-th suspected abnormal day. .Will Days with a value greater than or equal to 0.7 that are suspected to be abnormal are recorded as abnormal days, while those below this value are recorded as normal days. The specific value of the second threshold can be set by those skilled in the art based on clinical practice or experience, and this application will not elaborate on this.

[0052] As an example, updating outliers Satisfy the following formula:

[0053]

[0054] wherein, represents the mean value of all arbitrary two-dimensional data in the yth suspected abnormal day, The greater the better, the better the synergy of multi-dimensional data in the yth suspected abnormal day, represents the mean value of all dimensional data in the yth suspected abnormal day and the reference day, represents the interval days between the yth suspected abnormal day and the reference day. The fewer the interval days, the more consistent the user's physical condition, and the more reliable the represents the deviation of all dimensional data in the yth suspected abnormal day and the reference day. The better the synergy of multi-dimensional data in the suspected abnormal day, and the greater the deviation of all dimensional data from the reference day, the more abnormal the multi-dimensional data of the user in this day, and the abnormal lung function data of the user may be a signal of disease exacerbation.

[0055] Based on the above technical solution, the application calculates an updated and more reliable abnormal value by comprehensively considering the deviation, the synergy of multi-dimensional data (the mean value of similarity), and the time proximity (interval days). In this way, the application realizes secondary verification and refinement of the preliminary screened "suspected abnormal day". Only those that show significant, synergistic and recent abnormalities in multi-dimensional physiological indicators will be finally determined as true abnormal days. This can filter accidental factors and noise interference, and provide data quality for subsequent risk level assessment.

[0056] Next, the process of determining the risk level by the processing unit will be described in detail:

[0057] As a possible implementation manner, the processing unit is specifically configured to: determine at least one disease exacerbation stage of the target user based on the abnormal days in the observation stage, the disease exacerbation stage including a plurality of consecutive abnormal days; determine the risk level of the target user based on the exacerbation intensity of the disease exacerbation stage, the disease management ability, and the time interval between adjacent disease exacerbation stages, wherein the exacerbation intensity is used to represent the exacerbation severity and duration of the disease exacerbation stage, and the disease management ability is used to represent the ability of the target user to control and maintain the disease.

[0058] Based on the above technical solution, the application can analyze the risk level of the user from the aspect of the disease exacerbation stage, and introduces the dynamic evaluation dimension of disease management ability. In this way, the application can evaluate the overall disease fluctuation pattern and self-management effectiveness of the user in a period of time, rather than just the static lung function value, so that the risk assessment result can better reflect the individual differences and real long-term risk trend of the user.​​​

[0059] The following describes in detail the process of determining the deterioration intensity, the disease management capability, and the time interval of the disease deterioration stage by the processing unit:

[0060] As a possible implementation manner, the processing unit is specifically configured to: determine an updated abnormal value of each abnormal day in any disease deterioration stage; fit the updated abnormal values of any disease deterioration stage to obtain a third fitting curve, and determine a slope normalization value of each abnormal day of any disease deterioration stage based on the third fitting curve; multiply the updated abnormal value of any abnormal day by the slope normalization value to obtain a first product; accumulate the first products of each abnormal day to obtain a first accumulated value; calculate a time proportion of the disease deterioration stage in the observation stage; and take the product of the first accumulated value and the time proportion as the deterioration intensity of any disease deterioration stage.

[0061] As a possible implementation manner, the processing unit is specifically configured to: determine the deterioration intensity of any disease deterioration stage, a slope normalization value of a deterioration trend, and a duration of a disease stable stage after any disease deterioration stage, wherein the slope normalization value of the deterioration trend is a normalization value of a slope of a fitting straight line obtained by linear fitting of the updated abnormal values of the deterioration stage; the disease stable stage includes a plurality of continuous normal days; a normal day is a date other than an abnormal day in the observation stage; multiply the deterioration intensity of any disease deterioration stage by the corresponding slope normalization value to obtain a second product; multiply the second product by the reciprocal of the duration of the disease stable stage to obtain a third product; take the opposite of the third product as an index, calculate the power of a natural constant e, and obtain the disease management capability.

[0062] It should be noted that in the treatment process of COPD, the user needs to receive medical intervention for a long time. Due to the differences in age, living environment, and self-management capability of different COPD users, if the user does not use bronchodilators regularly, stops medication arbitrarily, or is exposed to inducing factors such as smoking, the user's condition will enter a deterioration stage. After entering this stage, because the user may use antibiotics and other drugs to control infection, airway inflammation will be gradually inhibited, and the condition will return to a stable stage. Therefore, the application can determine the risk level of the user based on the relevant performance of the user in the disease deterioration stage and the stable stage.

[0063] Optionally, in a preset time period, an abnormal day is marked as 1, and a normal day is marked as 0. Thus, a sequence composed of 0 and 1 is obtained. A stage composed of continuously adjacent 1s is recorded as a disease deterioration stage, and a stage composed of continuously adjacent 0s is recorded as a disease stable stage.

[0064] The deterioration intensity of the e-th disease deterioration stage is calculated as follows: wherein Y represents the number of abnormal days in the e-th disease deterioration stage,​ denotes the total number of days, denotes the updated abnormal value of the yth abnormal day in the e th exacerbation phase, denotes the slope normalization value corresponding to the updated abnormal value of the yth abnormal day in the e th exacerbation phase. The greater the value is, the faster the FEV1 / FVC ratio decreases, and the more rapidly the exacerbation trend is. In this application, normalization is used, unless otherwise specified, which is maximum-minimum normalization. Among them, the maximum and minimum values are preset empirical extreme values based on a large amount of historical experimental data. If the calculation result exceeds the interval [0, 1], it is limited in the interval [0, 1] through a truncation function (i.e., if the result is less than 0, 0 is taken, and if the result is greater than 1, 1 is taken), so as to eliminate the influence of abnormal values on the evaluation index.

[0065] In the above exacerbation intensity calculation formula, denotes the overall exacerbation effect of the e th exacerbation phase, denotes the time proportion of the e th exacerbation phase in the entire observation period. The greater the overall exacerbation effect of the e th exacerbation phase is, and the greater the time proportion in the entire observation period is, the more serious the damage to the user's respiratory function of the e th exacerbation phase is, and the longer the time is, the greater the possibility of the user's condition developing into acute exacerbation is, and the higher the corresponding early warning risk level should be.

[0066] obtain the updated abnormal value sequence of all days in the e th exacerbation phase }. The least square method is used to obtain the fitting straight line of the sequence.

[0067] calculate the condition management ability of the user in the e th exacerbation phase , wherein, denotes the normalization value of the slope of the fitting straight line of the e th exacerbation phase, denotes the exacerbation intensity of the e th exacerbation phase. denotes the duration of the next stable phase after the e th exacerbation phase. The smaller the value is, the more difficult the user is to maintain a stable condition after experiencing the e th exacerbation, and the worse the user's management ability is.

[0068] In the above condition management ability calculation formula, denotes the loss of control of the user's condition in the e th exacerbation phase. The greater the loss of control of the user's condition in the e th exacerbation phase is, and the shorter the stable condition maintenance time is, the higher the risk of the user's condition quickly turning from stable to fluctuation or exacerbation is, and the weaker the user's management ability is, thereby leading to repeated exacerbation of the condition, and the higher the corresponding risk level is.

[0069] obtaining all sequences of time intervals of adjacent exacerbation stages of the disease{ }Based on this, the application obtains the exacerbation intensity of the exacerbation stage of the disease, the disease management ability of the user, and the sequence of time intervals of the exacerbation stage of the disease through the above process.

[0070] The following is a detailed description of the process of determining the risk level of the target user by the processing unit based on the exacerbation intensity of the exacerbation stage of the disease, the disease management ability, and the time interval of adjacent exacerbation stages of the disease:

[0071] As a possible implementation, the processing unit is specifically configured to: fit the time sequence of the time interval of adjacent exacerbation stages of the disease, take the normalized value of the slope of the fitted straight line as the exacerbation interval trend; take the product of the reciprocal of the disease management ability and the reciprocal of the exacerbation interval trend as the basic risk value; take the reciprocal of the time interval between the most recent exacerbation stage of the disease and the current time as the time-sensitive factor; multiply the basic risk value and the time-sensitive factor, and normalize the product to determine the risk level of the target user.

[0072] Optionally, the risk level of the user's disease at the current time satisfies the following formula:

[0073]

[0074] wherein, represents{ }the normalized value of the slope of the fitted curve, The smaller the value is, the shorter the interval between the two exacerbations is, the shorter the stable period of the disease is, and the higher the risk level is. represents the disease management ability of the user in the most recent exacerbation stage of the disease, The higher the value is, the more effective the user's intervention measures in the exacerbation stage are, and the smaller the damage of the exacerbation of the disease to the lung function is. represents the time interval between the most recent exacerbation stage of the disease and the current time, and the smaller the time interval is, the greater the reference value of the risk level at the current time is.

[0075] In a possible implementation, after determining the risk level of the user's disease, it is determined whether the risk level of the user's disease is greater than a third threshold value, and if greater than or equal to the third threshold value, it is determined that the patient is in a high-risk state; if the risk level is less than the third threshold value and greater than or equal to a fourth threshold value, it is determined that the patient is in a medium-risk state; and if the risk level If the fourth threshold value is less than the third threshold value, it is determined that the patient is in a low-risk state. As an example, the third threshold value is 0.8, and the fourth threshold value is 0.5. The specific values of the third threshold value and the fourth threshold value can be set by a person skilled in the art based on clinical practice or experience, and the present application does not make redundant descriptions here.

[0076] Optionally, different warnings can be given in different risk states. For example, when it is determined that the patient is in a high-risk state, the warning information sent by the system includes: user basic information (name, medical record number), current risk level Specific values, key abnormal data triggering high risk, such as FEV1 / FVC decreasing by 20% compared with the reference, oxygen saturation being less than 90%, and respiratory rate being greater than 24 times per minute.

[0077] When it is determined that the patient is in a medium-risk state, the system prompts the user that the lung function fluctuation can be caused by insufficient treatment compliance or environmental stimulation, and medical staff can strengthen medication guidance through telephone, online consultation and the like, such as clearly defining the medication time and the correct operation method of the inhalation device, to prevent the disease from further deteriorating.

[0078] When it is determined that the patient is in a low-risk state, the system prompts the user to strengthen daily management to prevent the risk from further increasing, such as prompting the user to take medication on time and in the right amount, and prohibiting unauthorized drug withdrawal.

[0079] The above describes in detail the scheme of the intelligent early warning system for dynamic deterioration of COPD provided by the present application.

[0080] As shown in FIG. 1, Figure 2 The present application also provides a flowchart of an intelligent early warning method for dynamic deterioration of COPD, as shown in FIG. 2, which includes the following steps: Figure 2

[0081] Step 201: determining a suspected abnormal day according to lung function time series data.

[0082] Step 202: determining the deviation degree of the multi-dimensional physiological time series data of the suspected abnormal day and the multi-dimensional physiological time series data of the reference day and the similarity of the different dimensional physiological time series data deviation degrees.

[0083] Step 203: determining an abnormal day from the suspected abnormal day based on the deviation degree and the similarity.

[0084] Step 204: determining the risk level of the dynamic deterioration of COPD of the target user based on the abnormal day.

[0085] Step 205: performing risk warning based on the risk level of the dynamic deterioration of COPD of the target user.

[0086] ​The specific implementation of each of the above steps can refer to the description in the foregoing system, and the present application will not make any further description.

[0087] It should be noted that the above-mentioned embodiment sequence of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0088] Each of the embodiments in the specification is described in a progressive manner, and the same or similar parts between each of the embodiments can be referred to each other, and each of the embodiments mainly describes the difference from other embodiments.

Claims

1. An intelligent early warning system for dynamic exacerbation of chronic obstructive pulmonary disease, characterized in that, The system comprises: a data acquisition unit configured to acquire lung function time series data and multi-dimensional physiological time series data of a target user in an observation stage; the observation stage comprises a plurality of consecutive dates; a processing unit configured to determine a suspected abnormal day according to the lung function time series data, the suspected abnormal day being a date with a lung function data change degree greater than a first threshold value; determine a deviation degree of multi-dimensional physiological time series data of the suspected abnormal day and multi-dimensional physiological time series data of a reference day and a similarity of different dimensional physiological time series data deviation degrees, the reference day being a date with the smallest lung function data abnormal value and the best lung ventilation function; determine an abnormal day from the suspected abnormal days based on the deviation degree and the similarity, and determine a chronic obstructive pulmonary disease condition dynamic exacerbation risk level of the target user based on the abnormal day; and perform risk warning based on the chronic obstructive pulmonary disease condition dynamic exacerbation risk level of the target user; the processing unit is specifically configured to: fit target dimensional physiological time series data of a target suspected abnormal day to obtain a first fitting curve, and fit physiological time series data of the target dimension of the reference day to obtain a second fitting curve; the target suspected abnormal day is one of the suspected abnormal days, and the target dimensional physiological time series data is physiological time series data of one dimension in the multi-dimensional physiological time series data; calculate absolute values of data differences of the first fitting curve and the second fitting curve at each time point, and trend weights at each time point, wherein if the slope directions of the first fitting curve and the second fitting curve are the same at a time point, the trend weight is a first value, and if not, the trend weight is a second value, the second value being greater than the first value; based on the trend weight at each time point, sum the absolute values of the differences at the time point after weighting, and normalize the sum to obtain a deviation degree of the target dimension of the target suspected abnormal day; the average of the deviation degrees of each dimension of the target suspected abnormal day is taken as the deviation degree of the target suspected abnormal day; the processing unit is specifically configured to: determine a deviation degree time series sequence of first dimensional physiological time series data and a deviation degree time series sequence of second dimensional physiological time series data; the first dimensional physiological time series data and the second dimensional physiological time series data are physiological time series data of one dimension in the multi-dimensional physiological time series data, and the first dimensional physiological time series data and the second dimensional physiological time series data are different; the deviation degree time series sequence comprises deviation degrees at different time points; the similarity of the deviation degree time series sequence of the first dimensional physiological time series data and the deviation degree time series sequence of the second dimensional physiological time series data is taken as the similarity of the first dimensional physiological time series data and the second dimensional physiological time series data.

2. The intelligent early warning system for dynamic exacerbation of COPD according to claim 1, wherein, The lung function time series data comprises forced expiratory volume in one second and forced vital capacity of each day in multiple days; and the processing unit is specifically configured to: calculate a first ratio of forced expiratory volume in one second and forced vital capacity of each day; normalizing a difference value of the first ratio of each day and the first ratio of the previous day as an initial abnormal value of the pulmonary function data of each day; marking a date with the initial abnormal value greater than the first threshold value as the suspected abnormal day.

3. The intelligent early warning system for dynamic exacerbation of COPD conditions as claimed in claim 2 wherein, The processing unit is further configured to: mark a date with the initial abnormal value less than or equal to the first threshold value as an initial normal day; select, from a plurality of stable stages, a stable stage with the most initial normal days as a reference stage, the stable stage being a plurality of consecutive initial normal days; calculate a ventilation function of the target user of each day in the reference stage, the ventilation function being positively correlated with the first ratio and negatively correlated with the initial abnormal value; mark an initial normal day with the largest ventilation function value in the reference stage as the reference day.

4. The intelligent early warning system for dynamic exacerbation of COPD according to claim 1, wherein, The processing unit is specifically configured to: calculate an updated abnormal value of the target suspected abnormal day based on a deviation degree of the target suspected abnormal day, a similarity average of all-dimensional physiological time series data of the target suspected abnormal day, and a number of interval days between the target suspected abnormal day and the reference day, the updated abnormal value being positively correlated with the deviation degree and the similarity average and negatively correlated with the number of interval days; if the updated abnormal value of the target suspected abnormal day is greater than a second threshold value, mark the target suspected abnormal day as an abnormal day.

5. The intelligent early warning system for dynamic exacerbation of COPD according to claim 2, wherein, The processing unit is specifically configured to: determine at least one exacerbation stage of the target user based on the abnormal days in the observation stage, the exacerbation stage including a plurality of consecutive abnormal days; determine a risk level of the target user based on an exacerbation intensity of the exacerbation stage, a disease management capability, and a time interval between adjacent exacerbation stages, the exacerbation intensity being used to represent a severity and duration of the exacerbation stage, and the disease management capability being used to represent an ability of the target user to control and maintain the disease.

6. The intelligent early warning system for dynamic exacerbation of COPD according to claim 5, wherein, The processing unit is specifically configured to: determine an updated abnormal value of each abnormal day in any exacerbation stage; fit a third fitting curve of the updated abnormal values of the any exacerbation stage, and determine a slope normalization value of each abnormal day in the any exacerbation stage based on the third fitting curve; multiply the updated abnormal value of any abnormal day by the slope normalization value to obtain a first product; accumulate the first product of each abnormal day to obtain a first accumulated value; calculate a time proportion of the exacerbation stage in the observation stage; multiply the first accumulated value by the time proportion to obtain an exacerbation intensity of the any exacerbation stage.

7. The intelligent early warning system for dynamic exacerbation of COPD according to claim 6, characterized in that, The processing unit is specifically configured to: determine an exacerbation intensity of the any exacerbation stage, a slope normalization value of an exacerbation trend, and a duration of a stable stage after the any exacerbation stage, the slope normalization value of the exacerbation trend being a normalization value of a slope of a fitting straight line obtained by linear fitting of the updated abnormal values of the exacerbation stage, and the stable stage including a plurality of consecutive normal days, the normal day being a date in the observation stage other than the abnormal day. multiplying the deterioration intensity of any of the deterioration stages by a corresponding slope normalized value to obtain a second product; multiplying the second product by an inverse of a duration of the stable stage to obtain a third product; taking an exponential function with the third product as an exponent and a natural constant e as a base to obtain the condition management capability.

8. The intelligent early warning system for dynamic exacerbation of COPD according to claim 5, wherein, The processing unit is specifically configured to: fit a time series of time intervals of adjacent deterioration stages, and take a normalized value of a slope of a fitted straight line as a deterioration interval trend; take a product of an inverse of the condition management capability and an inverse of an inverse of the deterioration interval trend as a basic risk value; take an inverse of a time interval between a most recent deterioration stage closest to a current time and the current time as a time-sensitive factor; multiply the basic risk value by the time-sensitive factor, and normalize the product to determine a risk level of the target user.

Images